{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RO7JFQPOR5C3UGFIROXNX6EGKY","short_pith_number":"pith:RO7JFQPO","canonical_record":{"source":{"id":"2108.03614","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-08T11:34:37Z","cross_cats_sorted":[],"title_canon_sha256":"21c8ac7887b645dd1169db5cd58788a45568d44d574070dbf6817ece9e61cbe6","abstract_canon_sha256":"ee2dec61e8ca956e15cc15ca8572e2dbe54799eb103feffa94076a990fe48c0c"},"schema_version":"1.0"},"canonical_sha256":"8bbe92c1ee8f45ba18a88baedbf8865616f5388bef2910202aa2db95bb21dba9","source":{"kind":"arxiv","id":"2108.03614","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.03614","created_at":"2026-07-05T03:04:07Z"},{"alias_kind":"arxiv_version","alias_value":"2108.03614v1","created_at":"2026-07-05T03:04:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.03614","created_at":"2026-07-05T03:04:07Z"},{"alias_kind":"pith_short_12","alias_value":"RO7JFQPOR5C3","created_at":"2026-07-05T03:04:07Z"},{"alias_kind":"pith_short_16","alias_value":"RO7JFQPOR5C3UGFI","created_at":"2026-07-05T03:04:07Z"},{"alias_kind":"pith_short_8","alias_value":"RO7JFQPO","created_at":"2026-07-05T03:04:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RO7JFQPOR5C3UGFIROXNX6EGKY","target":"record","payload":{"canonical_record":{"source":{"id":"2108.03614","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-08T11:34:37Z","cross_cats_sorted":[],"title_canon_sha256":"21c8ac7887b645dd1169db5cd58788a45568d44d574070dbf6817ece9e61cbe6","abstract_canon_sha256":"ee2dec61e8ca956e15cc15ca8572e2dbe54799eb103feffa94076a990fe48c0c"},"schema_version":"1.0"},"canonical_sha256":"8bbe92c1ee8f45ba18a88baedbf8865616f5388bef2910202aa2db95bb21dba9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:04:07.779329Z","signature_b64":"B6TMS4vuRm/8O4tFQTmA7Vdng6lzI1AOEYzMW+krCAliSYl4Eu0nTN3YYGOaEzkJSKpqbuDarQghYIUhesicCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8bbe92c1ee8f45ba18a88baedbf8865616f5388bef2910202aa2db95bb21dba9","last_reissued_at":"2026-07-05T03:04:07.778874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:04:07.778874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.03614","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:04:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yhe9oFfgIKTB/56lF2J3U8toPZ6i92jBApnTAcLNn6xVjg1iFpgNDLA1El1FZSRdFyklJ60kBGhKt+08twl4Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:49:01.588600Z"},"content_sha256":"f28dc2a2781db98ab72c8ad69708fdfef6b180e0087867167b2176ccf3615aee","schema_version":"1.0","event_id":"sha256:f28dc2a2781db98ab72c8ad69708fdfef6b180e0087867167b2176ccf3615aee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RO7JFQPOR5C3UGFIROXNX6EGKY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Monte Carlo DropBlock for Modelling Uncertainty in Object Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"C Krishna Mohan, Kumari Deepshikha, P.K. Srijith, Sai Harsha Yelleni","submitted_at":"2021-08-08T11:34:37Z","abstract_excerpt":"With the advancements made in deep learning, computer vision problems like object detection and segmentation have seen a great improvement in performance. However, in many real-world applications such as autonomous driving vehicles, the risk associated with incorrect predictions of objects is very high. Standard deep learning models for object detection such as YOLO models are often overconfident in their predictions and do not take into account the uncertainty in predictions on out-of-distribution data. In this work, we propose an efficient and effective approach to model uncertainty in objec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.03614","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2108.03614/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:04:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jgW1+uly3Kwt99ICd5aoDgi1U3jxCtO99FlthQcddFuW/9rzywqRwPppW/93BEEKuJ0tdyn7NRrUqVHixiY1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:49:01.588975Z"},"content_sha256":"71317be2fe95e5ab666afe960bc00eceb39555f5a155e40b465a012533156805","schema_version":"1.0","event_id":"sha256:71317be2fe95e5ab666afe960bc00eceb39555f5a155e40b465a012533156805"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RO7JFQPOR5C3UGFIROXNX6EGKY/bundle.json","state_url":"https://pith.science/pith/RO7JFQPOR5C3UGFIROXNX6EGKY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RO7JFQPOR5C3UGFIROXNX6EGKY/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T15:49:01Z","links":{"resolver":"https://pith.science/pith/RO7JFQPOR5C3UGFIROXNX6EGKY","bundle":"https://pith.science/pith/RO7JFQPOR5C3UGFIROXNX6EGKY/bundle.json","state":"https://pith.science/pith/RO7JFQPOR5C3UGFIROXNX6EGKY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RO7JFQPOR5C3UGFIROXNX6EGKY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RO7JFQPOR5C3UGFIROXNX6EGKY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ee2dec61e8ca956e15cc15ca8572e2dbe54799eb103feffa94076a990fe48c0c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-08T11:34:37Z","title_canon_sha256":"21c8ac7887b645dd1169db5cd58788a45568d44d574070dbf6817ece9e61cbe6"},"schema_version":"1.0","source":{"id":"2108.03614","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.03614","created_at":"2026-07-05T03:04:07Z"},{"alias_kind":"arxiv_version","alias_value":"2108.03614v1","created_at":"2026-07-05T03:04:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.03614","created_at":"2026-07-05T03:04:07Z"},{"alias_kind":"pith_short_12","alias_value":"RO7JFQPOR5C3","created_at":"2026-07-05T03:04:07Z"},{"alias_kind":"pith_short_16","alias_value":"RO7JFQPOR5C3UGFI","created_at":"2026-07-05T03:04:07Z"},{"alias_kind":"pith_short_8","alias_value":"RO7JFQPO","created_at":"2026-07-05T03:04:07Z"}],"graph_snapshots":[{"event_id":"sha256:71317be2fe95e5ab666afe960bc00eceb39555f5a155e40b465a012533156805","target":"graph","created_at":"2026-07-05T03:04:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2108.03614/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the advancements made in deep learning, computer vision problems like object detection and segmentation have seen a great improvement in performance. However, in many real-world applications such as autonomous driving vehicles, the risk associated with incorrect predictions of objects is very high. Standard deep learning models for object detection such as YOLO models are often overconfident in their predictions and do not take into account the uncertainty in predictions on out-of-distribution data. In this work, we propose an efficient and effective approach to model uncertainty in objec","authors_text":"C Krishna Mohan, Kumari Deepshikha, P.K. Srijith, Sai Harsha Yelleni","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-08T11:34:37Z","title":"Monte Carlo DropBlock for Modelling Uncertainty in Object Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.03614","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f28dc2a2781db98ab72c8ad69708fdfef6b180e0087867167b2176ccf3615aee","target":"record","created_at":"2026-07-05T03:04:07Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ee2dec61e8ca956e15cc15ca8572e2dbe54799eb103feffa94076a990fe48c0c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-08-08T11:34:37Z","title_canon_sha256":"21c8ac7887b645dd1169db5cd58788a45568d44d574070dbf6817ece9e61cbe6"},"schema_version":"1.0","source":{"id":"2108.03614","kind":"arxiv","version":1}},"canonical_sha256":"8bbe92c1ee8f45ba18a88baedbf8865616f5388bef2910202aa2db95bb21dba9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bbe92c1ee8f45ba18a88baedbf8865616f5388bef2910202aa2db95bb21dba9","first_computed_at":"2026-07-05T03:04:07.778874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:04:07.778874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B6TMS4vuRm/8O4tFQTmA7Vdng6lzI1AOEYzMW+krCAliSYl4Eu0nTN3YYGOaEzkJSKpqbuDarQghYIUhesicCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:04:07.779329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.03614","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f28dc2a2781db98ab72c8ad69708fdfef6b180e0087867167b2176ccf3615aee","sha256:71317be2fe95e5ab666afe960bc00eceb39555f5a155e40b465a012533156805"],"state_sha256":"9ac1a5ea619c3244bdad302a657ad5850a379b3ae31036c03d9748be10326ea6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8jIn/msQyq0B7EckLeA+dTF7WTl7QIX+sazJZkjgvxOxgZ3DGy8foHwiKMuhDOTNkCSymMCeZUalVBsFWuGTDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:49:01.594855Z","bundle_sha256":"cf6c70ed62e576f1dcce90c05b875b9f982d94d8e36f6ecebd78e64f380dd222"}}